Hardware · Intel
What AI models can the Intel N100 / N95 NAS (48 GB) run?
- RAM
- 48.0 GB
- Usable for models
- 40.3 GB
- Memory bandwidth
- 38 GB/s
- Runs models on
- CPU cores
- Released
- 2023
A NAS with this chip runs models on its processor cores, so memory speed sets the pace: small models (about 1-4B) answer at a usable speed, bigger ones are slow. We plan around 40.3 GB for models, what is left after the NAS system and its storage services. Models run in a container (Docker) or the maker’s app store, and speeds assume the NAS isn’t busy with storage work.
More about this hardware
| Maker | Intel |
|---|---|
| Type | NAS (network attached storage) processor |
| Share of memory for models | 84% (what the NAS system and its storage services typically leave free at this size) |
| Chip | Intel N100 / N95 |
| AI accelerator | Integrated graphics; NAS systems normally run models on the processor cores. |
| NAS models with this chip | Aiffro K100 · AOOSTAR WTR PRO N100 4 Bay NAS · AOOSTAR R1 N100 2-Bay NAS Mini PC · Beelink ME mini (Intel N95 / N150) · Beelink ME Pro (Intel N95 / N150) · CWWK N150-K / N355 Mini-ITX NAS motherboard (6x SATA, 2x i226-V) · Topton N8 6-bay NAS motherboard (Intel N100 / N150; sold elsewhere as MW-N100-NAS class board) · Maiyunda M1 / M1 Mini (N100 / N305), incl. quick-release Pro · Maiyunda M1S · Topton P5-4M 6-bay Pocket NAS (N100 / N150 / i3-N305 / Core 3 N355) · LincPlus LincStation N2 · LincPlus LincStation N2R · LincPlus LincStation S1 · TerraMaster F2-424 · TerraMaster F4-424 · TerraMaster F6-424 · TerraMaster F8 SSD · TerraMaster F4 SSD · TerraMaster F2-425 Plus · TerraMaster F4-425 Plus · UGREEN NASync DXP2800 · UGREEN NASync DXP4800 · IceWhale ZimaCube · IceWhale ZimaCube (N100) |
| Memory type | System RAM, shared with the NAS operating system and its storage services |
| Bandwidth figure | 38.4 GB/s, estimated, see the note below |
| Note | One profile for every NAS built on this chip. Memory speed is an estimate from the chip’s supported memory in a typical NAS fitting; a unit with one memory module runs slower than one with two. Speed assumes the NAS is not busy with storage work. |
| Specifications | aiffro.com |
Apps that run models well on the Intel N100 / N95 NAS (48 GB)
2 products with the Intel N100 / N95 NAS (48 GB)
Best LLMs for the Intel N100 / N95 NAS (48 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q4_K_M | 25.9 GB | 10.1 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q4_K_M | 25.9 GB | 10.1 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q4_K_M | 25.5 GB | 10.1 tok/s | Runs well |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | Q5_K_M | 32.3 GB | 10.0 tok/s | Runs well |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | Q4_K_M | 25.4 GB | 10.1 tok/s | Runs well |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Sage-A1.5 35B-A3B | Q4_K_M | 25.9 GB | 10.1 tok/s | Runs well |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 35B-A3B | Q4_K_M | 25.9 GB | 10.1 tok/s | Runs well |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | KAT-Coder V2.5 Dev (35B-A3B) | Q4_K_M | 25.1 GB | 10.1 tok/s | Runs well |
| 84Great quality (A) · 84 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Apodex 1.1 Mini (35B-A3B) | Q4_K_M | 25.9 GB | 10.1 tok/s | Runs well |
| 84Great quality (A) · 84 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 35B-A3B | Q4_K_M | 25.9 GB | 10.1 tok/s | Runs well |
| 95Excellent quality (A+) · 95 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 27B | Q8_0 | 33.8 GB | 0.6 tok/s | Very slow |
| 94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.3 33B | Q6_K | 32.7 GB | 0.7 tok/s | Very slow |
Best Image models for the Intel N100 / N95 NAS (48 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Fibo 2.0 Dev | FP16 | 27.7 GB | 76.7 min | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Ideogram 4 | FP8 | 29.9 GB | 76.7 min | Very slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 Turbo | Q8 GGUF | 31.3 GB | 45.5 min | Very slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image | FP16 | 34.0 GB | 75.0 min | Very slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | FP16 | 22.4 GB | 19.4 min | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | FP16 | 26.4 GB | 10.9 min | Very slow |
Best Video models for the Intel N100 / N95 NAS (48 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Bernini-R A14B (video generation + editing) | FP8 | 26.0 GB | 36.8 h | Very slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 I2V A14B | Q4 GGUF | 32.7 GB | 109.1 h | Very slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 T2V A14B | Q4 GGUF | 32.7 GB | 109.1 h | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | SCAIL-2 14B (character animation) | FP8 | 29.8 GB | 61.4 h | Very slow |
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanVideo 1.5 (8.3B) | FP8 | 38.4 GB | 92.1 h | Very slowtight fit |
Best Decision models for the Intel N100 / N95 NAS (48 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | 197 ms | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q8_0 | 8.4 GB | 28.8 s | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | Q8_0 | 12.8 GB | 58.8 s | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | Q8_0 | 4.7 GB | 4.3 s | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 115.9 s | Very slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | zerank-2 | Q8_0 | 8.4 GB | 28.8 s | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | Q8_0 | 4.7 GB | 4.3 s | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Shieldstral 1.0 3B | Q8_0 | 8.1 GB | 27.6 s | Very slow |
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.